Opus [1m] suffix and "with 1M context" label now depend on each model's 1M support

What

The context window is how much text a model can consider at once. Some models have a 1M-token window built in (native). Others offer it only when asked for (opt-in), which Claude Code does by adding [1m] to the model name. Claude Code now tracks each model's 1M support as "never", "native" or "optIn" instead of a yes or no:

• CLAUDE_CODE_DISABLE_1M_CONTEXT makes every model count as "never".
• Default Opus: [1m] is added to the default Opus model only when its support is "optIn". Models with a native 1M window no longer get [1m].
• Picking opus: when the opus alias points to a model with opt-in 1M, choosing it now resolves to that model with [1m]. The option label also shows the resolved model id.
• Subagents: an Opus-family subagent model gets [1m] when it lacks it and its 1M support is "optIn" on a first-party provider.
• Model picker: the Opus description shows "with 1M context" based on the selected model's support being "optIn", instead of one global check. Opus counts as 1M-eligible unless its support is "never".

Why

The model name shown for default Opus may change, and Opus subagents may now run with a larger context window, which can affect cost. The picker should stop claiming 1M context for Opus models that do not offer it.