Back to Signal Feed
CodeTracked since May 21, 2026

Add persistent Cursor MAX mode across model selection and session lifecycle

Adds end-to-end support for Cursor MAX mode by introducing a `:max` model selector flag and threading that state through model parsing/formatting, agent session state, and task-subagent startup so supported models can reliably run in 1M-context mode.

Cursor MAX mode`:max` selector flagSelectorFlagsAgentSession

What Happened

  • Adds end-to-end support for Cursor MAX mode by introducing a `:max` model selector flag and threading that state through model parsing/formatting, agent session state, and task-subagent startup so supported models can reliably run in 1M-context mode.
  • Adds end-to-end support for Cursor MAX mode by introducing a `:max` model selector flag and threading that state through model parsing/formatting, agent session state, and task-subagent startup so supported models can reliably run in 1M-context mode.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

Implemented MAX-mode as a first-class model capability (`maxMode`) that is parsed from model selectors, preserved in session state, applied in provider request construction, and inherited by subagent sessions, replacing ad-hoc flag handling with a shared selector/session flow tied to Cursor capability policy.

Why Track This

Why It Matters

Cursor users and operators can now keep expensive long-context runs in the intended 1M-context mode across model selection, resumes, and subagent creation, instead of being silently pulled back to a lower context setting mid workflow. The implementation wires `:max` through selector parsing/formatting and session lifecycle APIs (`setCursorMaxMode`, `getCursorMaxMode`) while propagating policy during startup and subagent initialization, so behavior is consistent; track parser regressions with non-Cursor models, capability detection mistakes that could enable/disable MAX incorrectly, and any gaps in MAX inheritance when sessions are rehydrated.

Impact

Cursor users and operators can now keep expensive long-context runs in the intended 1M-context mode across model selection, resumes, and subagent creation, instead of being silently pulled back to a lower context setting mid workflow. The implementation wires `:max` through selector parsing/formatting and session lifecycle APIs (`setCursorMaxMode`, `getCursorMaxMode`) while propagating policy during startup and subagent initialization, so behavior is consistent; track parser regressions with non-Cursor models, capability detection mistakes that could enable/disable MAX incorrectly, and any gaps in MAX inheritance when sessions are rehydrated.

What To Watch Next

  • Watch whether Cursor MAX mode becomes a repeated pattern.
  • Track follow-up changes around Tool Calling.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: cursor_max_mode_state_loss_on_resume, selector_parsing_regression_colon_suffix.
Open Topic TimelineOpen Technical EventOpen Original Sourcecursor_max_mode_state_loss_on_resume / selector_parsing_regression_colon_suffix / wrong_max_capability_detection / subagent_max_mode_inheritance_break / usage_stats_miscount_with_cumulative_tokens

Supporting Evidence

GITHUB PULL REQUESTHigh Trust

can1357/oh-my-pi PR #1098: feat(cursor-agent): Cursor MAX mode support

MAX mode is surfaced as a step in the `/model` selector menu, persists across session resume, and propagates correctly to subagents spawned via `task`.