Skip to content

🌐 日本語

Part 2: Understanding the Context Window ​

NOTE

Learn the structure of the LLM's "thinking space."
The physical basis for why the structural problems in Part 1 occur is here.
Window constraints are not product-specific. Claude Code is used as a concrete example of injection.

Three Concepts to Fix First ​

Token, Context, and Context Window are prerequisites for every later design decision. Each is defined on its own page.

DocumentContent
TokenThe LLM's processing unit—neither character nor word
ContextEverything passed in one inference; history is resent each turn
Context WindowThe ceiling, and the fact that the safe range is smaller
How the three relateRelationship diagram for unit, content, and ceiling

What You'll Learn in This Part ​

DocumentContent
Chat / SessionWhy Context grows over time
What the LLM "Sees"The view inside the window
Injection TimingWhen each setting enters Context
Context BudgetHow to allocate finite tokens

Why This Sits Between Part 1 and Part 3 ​

Part 1 shows what goes wrong. Part 2 shows the structure of the thinking space. Part 3 onward shows where to put controls.

Copying settings without knowing runtime constraints hides why those limits exist. This Part is that physical layer.


Previous: Part 1: Understanding LLM Structural Constraints

Next: Token — The LLM's Processing Unit

Released under the CC BY 4.0 License.