When an AI agent like Claude Code nears its context limit where automatic compaction might fail, a useful hack is instructing it to "write a markdown file of your process and your progress and what you have left to do." This creates a manual state transfer mechanism for starting a new session.

Instead of starting new chats for every task, use single, long-running 'monothreads' for each major workstream. Advanced context compaction in tools like Codex allows these threads to persist memory over time, turning the AI from a simple Q&A bot into an ongoing project collaborator with deep context.

When an AI's context window is nearly full, don't rely on its automatic compaction feature. Instead, proactively instruct the AI to summarize the current project state into a "process notes" file, then clear the context and have it read the summary to avoid losing key details.

A key weakness of LLMs, the tendency to forget details in long conversations ("context rot"), is being overcome. Claude Opus 4.6 scored dramatically higher than its predecessor on this task, a crucial step for building reliable AI agents that can handle sustained, multi-step work.

Long, continuous AI chat threads degrade output quality as the context window fills up, making it harder for the model to recall early details. To maintain high-quality results, treat each discrete feature or task as a new chat, ensuring the agent has a clean, focused context for each job.

Before ending a complex session or hitting a context window limit, instruct your AI to summarize key themes, decisions, and open questions into a "handoff document." This tactic treats each session like a work shift, ensuring you can seamlessly resume progress later without losing valuable accumulated context.

Long-running AI agent conversations degrade in quality as the context window fills. The best engineers combat this with "intentional compaction": they direct the agent to summarize its progress into a clean markdown file, then start a fresh session using that summary as the new, clean input. This is like rebooting the agent's short-term memory.

Seemingly complex features like long-term memory and skill creation are fundamentally clever systems for managing an AI's limited context window. The "harness" efficiently loads and unloads relevant information (memories, skills) at the precise moment it's needed, rather than keeping it all in context constantly.

To enable long-horizon tasks, Cursor incorporates "self-summarization" directly into its RL loop. The model learns to compact its own history and restart its context window with the summary. This allows it to operate over millions of tokens despite a nominal 200k context limit.