CCAR-F - Context Management & Reliability - Section 5.1

Manage conversation context to preserve critical information across long interactions.

Progressive summarisation quietly destroys numbers, percentages, dates and stated customer expectations, and the lost in the middle effect means long inputs are processed reliably at their start and end while middle findings get omitted. Candidates should hold transactional facts in a persistent case-facts block outside summarised history, trim verbose tool output to the relevant fields before it accumulates, and place key findings at the start of aggregated input.

progressive summarisation risklost in the middle effectpersistent case facts blocktool output trimmingposition-aware input ordering

Practice question for this objective

Free sampleContext Management & Reliabilitymedium

Each get_customer call on the Customer Support Resolution Agent returns a full 24 month order history averaging 18,000 tokens of JSON. Sessions now compact after roughly 12 turns, median handling latency has risen to 31 seconds, and reviewers note that the agent loses the customer's earlier statements once compaction starts. A typical contact uses two or three fields from that payload. Which change most effectively addresses it?

  • ARaise the compaction threshold so the harness tolerates a much larger transcript before it begins summarising the earlier turns.
  • BInstruct the agent in the system prompt to disregard the order history fields it does not need when it reads a get_customer result.
  • CChange get_customer to return the account summary and the recent order identifiers, with the full history fetched on demand by a separate call. Correct
  • DDelegate every get_customer call to a subagent through the Task tool so that the large payload lands in a separate context window.
Trim verbose tool results at the tool boundary so that bulky payloads never enter the conversation context in the first place. Everything a tool returns becomes part of the input on every subsequent turn, so an oversized result is paid for repeatedly and pushes the session into compaction where genuinely irreplaceable material, the customer's own words, is summarised away. Reshaping the tool contract to return a summary plus identifiers, with detail available on request, is the only option that reduces the token load rather than relocating or deferring it.

Why A is wrong: Tempting because compaction is where the customer statements are lost, so deferring it appears to protect them. It is wrong because the payload still consumes the same share of every input, so latency and cost stay high and the loss returns as soon as the higher threshold is reached.

Why B is wrong: Tempting because ignoring irrelevant fields is exactly what a human would do and the instruction is easy to write. It is wrong because the tokens are already in the context once the result is returned, so reading behaviour changes nothing about compaction pressure, latency or spend.

Why C is correct: Correct because it removes the tokens at their source: the tool returns what a contact actually consumes, the rare case that needs deep history retrieves it explicitly, and compaction pressure, latency and cost all fall together.

Why D is wrong: Tempting because subagent isolation is a real technique for keeping bulky work out of a coordinator's context. It is wrong because it is over-engineered for a payload the tool itself should shrink, and it adds a round trip and a summarisation boundary to every identity lookup.

See more CCAR-F practice questions, answers explained.

More in this domain

Back to all Context Management & Reliability objectives, or the CCAR-F cert hub.

Examworthy is not affiliated with or endorsed by Anthropic. Original, blueprint-aligned practice material only.