Context Window

Bytes, characters, tokens: which one gets billed and how do they relate?

Sequence length vs context window, what is the practical distinction and which one drives KV cache size?

What is the context window of an LLM?

Your input is 9,000 tokens but max_length is 8,192. What are your truncation options?

An LLM never sees raw text. So what does it actually process?

Someone confuses 'sequence length' with 'context window'. How do you correct them?

Where does an agent keep short-term state during a single task?

What causes context pollution in a long-running agent?

What does a model's 'context window' mean and what does it include?

Flashcard: what is a token in LLM prompting and why does it matter for cost and context?

What does the max_tokens parameter control in an LLM API call?

You have 500KB of relevant documentation that exceeds the 200K-token context window of your production model. How should you choose between context stuffing (fit what you can) and RAG retrieval?

Flashcard: what role does the LLM's context window play in a RAG pipeline?

How would you build an accurate token budget estimator for a multilingual RAG application?

Distinguish short-term vs long-term agent memory and name a failure mode specific to each

Why does token cost in a naive agent loop grow quadratically with step count?