Retrieval per Turn

Paying for the search every turn

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

An agent that retrieves on every turn pays for the retrieval on every turn. The document does not replace the last one, it joins it: each turn adds its own chunks to the window alongside the question and the answer, so a turn costs far more than the words anyone typed. At two tokens a word, even a short document doubles what a turn costs, and the conversation around it is the smaller part. That is why an agent with retrieval runs out of window in a handful of turns while a plain chat runs for dozens.

---

---

⬇ Retrieval per Turn worksheet (3 pages)

---

Next:
8. Search Rounds