Auto Compaction - Claude Code
Background context summarization when the window starts filling up.
Auto compaction is how Claude Code survives marathon sessions without losing the thread. When the window starts filling, Claude summarizes older turns in place.
What it does
As context approaches capacity, Claude runs a summarization pass on older turns - preserving key decisions, file paths, and state - while dropping verbose tool output and stale exchanges. The working memory shrinks without losing the important history. PreCompact and PostCompact hooks let you react around the event.
When to use it
- Long sessions that would otherwise hit the context ceiling.
- Any marathon where you want Claude to stay coherent across many turns.
- Working on tasks that need broad state but not full history.
- Pair with hooks when you want to snapshot, log, or replace compaction behavior.
Gotchas
- Compaction is lossy. Important details might get summarized away.
- Write critical decisions to disk (notes, TODO.md, commits) so compaction can't drop them.
- Custom compaction via hooks is powerful but easy to get wrong. Start conservative.
Official docs: https://code.claude.com/docs/en/how-claude-code-works.md#when-context-fills-up
Technical content at the intersection of AI and development. Building with AI agents, Claude Code, and modern dev tools - then showing you exactly how it works.
Get the weekly deep dive
Tutorials on Claude Code, AI agents, and dev tools - delivered free every week.
Was this helpful?
Related Guides
Related Tools
Claude Code
Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory...
View ToolCodeburn
Interactive TUI dashboard that shows exactly where your Claude Code and Cursor tokens are going, in real time.
View ToolClaude Opus 4.7
Anthropic's flagship reasoning model. Best-in-class for coding, long-context analysis, and agentic workflows. 1M token c...
View ToolCursor
AI-native code editor forked from VS Code. Composer mode rewrites multiple files at once. Tab autocomplete predicts your...
View ToolRelated Videos

Nimbalyst: The Open-Source Visual Workspace for Building with Codex and Claude Code
Nimbalyst Demo: A Visual Workspace for Codex + Claude Code with Kanban, Plans, and AI Commits Try it: https://nimbalyst.com/ Star Repo Here: https://github.com/Nimbalyst/nimbalyst This video demos N...

Composio: Connect OpenClaw & Claude Code to 1,000+ Apps via CLI
Composio: Connect AI Agents to 1,000+ Apps via CLI (Gmail, Google Docs/Sheets, Hacker News Workflows) Check out Composio here: http://dashboard.composio.dev/?utm_source=Youtube&utm_channel=0426&utm_...

Claude Code Channels in 8 Minutes
Anthropic has released Channels for Claude Code, enabling external events (CI alerts, production errors, PR comments, Discord/Telegram messages, webhooks, cron jobs, logs, and monitoring signals) to b...
Related Posts

Claude Opus 4.8 Is an Agent Honesty Release
Claude Opus 4.8 looks like a benchmark bump, but the developer story is better honesty, dynamic workflows, and effort co...

Anthropic Sonnet 4.5 in Claude Code
Anthropic's Claude Sonnet 4.5 isn't just another model increment. The company claims they've observed it maintaining foc...

AI Code Attribution Needs Defect Forensics, Not Vibes
The rsync Claude debate shows why teams need reproducible defect forensics before AI attribution becomes a public blame...

Security Agents Need Repro Harnesses, Not More Scan Prompts
Anthropic's open-source vulnerability harness shows where AI security work is going: reproducible exploit loops, separat...

AI Agent Containment Needs a Capability Ledger
Anthropic's Claude containment writeup points to the next security layer for coding agents: deterministic capability led...

The Model, IDE, CLI, and Agent Framework Changes That Actually Matter
The AI coding market is noisy. The changes that matter are easier to spot when you separate model capability, editor loo...
