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.
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 Tool
Claude Opus 4.7
Anthropic's flagship reasoning model. Best-in-class for coding, long-context analysis, and agentic workflows. 1M token c...
View ToolConductor
Mac app for running parallel Claude Code, Codex, and Cursor agents in isolated workspaces. Watch every agent work at onc...
View ToolRelated Videos
Claude Code: NEW Remote Control, Auto Memory, Plugins & More
Anthropic's Big Claude Code & Cowork Update: Remote Control, Scheduled Tasks, Plugins, Auto Memory + New Simplify/Batch Skills The script recaps a consolidated update on new Anthropic releases across
Claude Code Can Now Automate Work in Chrome
In this video, learn to utilize Claude Code within Chrome to access new automation capabilities that were previously impossible. Leveraging your existing browser sessions, Claude Code enhances...
How to Run Claude Code For Hours Autonomously
Setting up Claude Code to Run Autonomously with Stop Hooks In this video, we dive into the setup and configuration of Claude Code to enable autonomous long-running scripts. We explore the...
Related Posts
Claude Outages Are a Workflow Design Problem
Claude outages and 529 overloads expose whether your AI coding workflow has checkpoints, receipts, model-switch paths, a...
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...
Make Your Coding Agents Talk: Voice Summaries with the Rime CLI
The Rime CLI streams natural-sounding text-to-speech straight from your terminal, so Claude Code, Codex, Devin, and Open...
How to Make Claude Code 10x Better at Design: Image and Video Assets From the Agent Loop
Claude Code and Codex can build a website in minutes, but the result often looks generic and obviously AI-generated. Hig...
Don't Paste the AI vs Vomit vs NoBuzz: AI Slop Tools Compared
dontpastetheai.com, Vomit, and NoBuzz hit Hacker News in the same week. A social contract, a local rewrite, and a second...
