# Context Window Packing

> Allocate a fixed token budget across system prompt, history, retrieved chunks, and tools on every call — so the window never silently overflows.

- **Category**: Agentic AI
- **Subcategory**: Memory
- **Canonical URL**: https://designpattern.fyi/patterns/context_window_packing/

---

## Description
**Intent**: Choose what fits in the context window each turn given a fixed token budget.
**Context**: Everything the model needs for the next call — system prompt, conversation history, retrieved chunks, tool definitions, current state — has grown past the model's maximum context window. Every single call now requires explicit decisions about what goes in and what stays out.
**Solution**: Define a packing policy. Reserve N tokens for system + tools + response. Allocate the rest across history (compressed), retrieved chunks (top-k after rerank), and current state. Apply eviction (drop oldest), summarization (compress), or selection (relevance-rank) policies. Audit token counts before each call.



## Use Cases
- Naive concatenation overflows the context window for realistic inputs.
- Some context (system prompt, tools, response reservation) is fixed and the rest must be allocated dynamically.
- Token counts can be audited before each call and the policy can be adjusted.






## Trade-offs


### Advantages

- Predictable, deterministic behavior at the window edge — no surprise truncation.

- Inspectable trade-offs — you can see exactly what got included and why.




### Considerations & Drawbacks

- Packing logic adds implementation complexity that grows with the number of context sources.

- Compression artifacts can degrade coherence in ways that are hard to detect.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/context-window-packing/)