A harbor-slip reservation tester’s pasted API log is silently cut off mid-stack-trace. Why should testers care whether prompt plus history fit the context window?
Select an answer to reveal the explanation.
Short Explanation
If the suitcase is overfull, something gets left on the bed—often without a loud alarm. When tokens exceed the window, parts of the prompt or history drop. Testers care because a mid-log cutoff hides evidence the model never saw.
Full Explanation
Prompt text plus conversational or pasted history is measured in tokens against the model’s context window. Overflow means some tokens are not considered, which can look like a silent mid-stack-trace cutoff. Chapter 1 expects that conceptual awareness; a hands-on token-counting lab is not the examinable skill here. Overflow does not retarget the model as classical ML, and stack traces do consume tokens like other text.