Where does the bug appear (feature/product)? Cursor IDE Describe the Bug Subagent Luna-5.6-Max-1M compresses context too early for the task it was launched for. Steps to Reproduce --- name: Verifier Pro model: gpt-5.6-luna[context=1m,reasoning=max,fast=false] description: Verifier Pro --- Expecte…

Hi @Artemonim ! Thanks for the report. I think I know what this bug is — could you toggle “Max Mode” on and see if that changes the behavior?

Yes, that sounds like a reason. [2026-07-13_15-45-23] Is this how it is intended or will it be corrected?

With the impending removal of Max Mode for usage-based plans, I imagine this will need to be corrected! I’ll still file a bug report for the team, however, as I can reproduce the issue myself.

@Colin I’m sorry for the off-topic, but could you also take a look at my issue in the GPT-5.6 feedback thread? [image] Share your Thoughts on GPT 5.6! Release Discussions @kevinn Fable noticed that GPT-5.6-Terra is billed at a higher price than advertised think…

A subagent with 1M context starts with 272k context

Support Bug Reports

Artemonim (Artemonim) July 13, 2026, 8:54pm 10

@Colin I’m sorry for the off-topic, but could you also take a look at my issue in the GPT-5.6 feedback thread?

Topic		Replies	Views
Early compression of the 1M Subagent context window (broken subagent resume, yep)) Bug Reports max-mode , context , subagents	3	88	August 28, 2026
Context keeps summarizing at 10-20% of total context window Bug Reports context	1	139	June 23, 2026
GLM 5.2 on MAX context, does not really have 1M context size Bug Reports max-mode , context	6	330	August 11, 2026
Incorrect context manipulation Bug Reports max-mode , context	5	165	July 11, 2026
Max Mode shows 300K context limit instead of 1M for all models (Opus 4.6, Sonnet 4.5, etc.) Bug Reports nightly , max-mode , context , anthropic	1	824	May 12, 2026

A subagent with 1M context starts with 272k context

Related topics