Growth per Turn

How a window fills, one turn at a time

Library › Context Problems

1. The Context Window

2. Window Occupancy

3. Growth per Turn

4. Remaining Space

5. Turn Budget

6. Retrieval Footprint

7. Retrieval per Turn

8. Search Rounds

9. Window Sizing

10. Truncation

11. Compaction

12. The Compaction Bill

13. Compacted Retrieval

14. The Compaction Threshold

15. Verbatim Tail

16. Stateless API

17. Retrieval Cost

18. Context Tax

19. Quadratic Cost

20. Cost Forecast

A conversation does not fill the window smoothly; it fills in blocks, one per turn, and every block has the same shape. Notice how few of each turn's tokens are the user's and how much is the model's reply: the agent spends most of its window on what it says, not on what it is asked. The system prompt is written once and never repeats, so after enough turns it stops mattering, while the turns keep coming at the same size each time.

---

⬇ Growth per Turn worksheet (2 pages)

---

Next:
4. Remaining Space