12  Task 3: The Context Limit Challenge

In this task, we will simulate a real-world scenario where you have “too much information” for the model to handle at once. We’ll use the rdocdump tool to create a massive text file from an R package.

12.1 Step 1: Generating the “Mega-File”

Open your terminal and run the following command to dump the entire documentation of the DemoTools package into a single text file:

# This uses rdocdump to pull the full text of the package from GitHub
# Note: You might need to install it first if not in the container
# remotes::install_github("e-kotov/rdocdump")
Rscript -e 'rdocdump::rdocdump("e-kotov/DemoTools", out = "demotools_dump.txt")'

12.2 Step 2: The Naive Reality Check

Now that you have demotools_dump.txt, try the “Naive” approach:

  1. Open the file in VS Code and copy all the text (it will be thousands of lines).
  2. Go to the OpenAI Tokenizer and paste it. How many tokens is it?
  3. Try pasting it into Google AI Studio or ChatGPT.
    • Does it fit?
    • Is it hard to scroll?
    • Imagine doing this for every question you have!

12.3 Step 3: The Agentic Solution

Now, let’s see how an agent handles this without blowing up the context window.

Launch the Gemini CLI or OpenCode agent and give it a broad task.

Prompt to try: > “I have a file called demotools_dump.txt. Read it and explain how the DemoTools package handles life table calculations. Provide a code example based on what you find.”

Observation: The agent cannot read the entire file at once because it has a safety limit (usually around 2000 lines). Watch how it pivots: - It might use grep_search to find “life table”. - It might read the file in small chunks using start_line and end_line. - It might use a “Context Mode” tool to index the file in a sandbox and only return the relevant sections.

12.4 Why this matters

By using an agent, you avoided: 1. Wasting money/tokens on thousands of lines of irrelevant documentation. 2. Confusing the model with too much noise. 3. Manual effort of hunting through a giant text file.


Tip: If the agent gets stuck, help it! You can say: “Use grep_search to find the life table functions in the dump file.”