Skip to main content
Session pruning trims old tool results from the context before each LLM call. It reduces context bloat from accumulated tool outputs (exec results, file reads, search results) without rewriting normal conversation text.
Pruning is in-memory only — it does not modify the on-disk session transcript. Your full history is always preserved.

​
Why it matters

Long sessions accumulate tool output that inflates the context window. This increases cost and can force compaction sooner than necessary. Pruning is especially valuable for Anthropic prompt caching. After the cache TTL expires, the next request re-caches the full prompt. Pruning reduces the cache-write size, directly lowering cost.

​
How it works

  1. Wait for the cache TTL to expire (default 5 minutes).
  2. Find old tool results for normal pruning (conversation text is left alone).
  3. Soft-trim oversized results — keep the head and tail, insert ....
  4. Hard-clear the rest — replace with a placeholder.
  5. Reset the TTL so follow-up requests reuse the fresh cache.

​
Legacy image cleanup

FluffBuzz also runs a separate idempotent cleanup for older legacy sessions that persisted raw image blocks in history.
  • It preserves the 3 most recent completed turns byte-for-byte so prompt cache prefixes for recent follow-ups stay stable.
  • Older already-processed image blocks in user or toolResult history can be replaced with [image data removed - already processed by model].
  • This is separate from normal cache-TTL pruning. It exists to stop repeated image payloads from busting prompt caches on later turns.

​
Smart defaults

FluffBuzz auto-enables pruning for Anthropic profiles: If you set explicit values, FluffBuzz does not override them.

​
Enable or disable

Pruning is off by default for non-Anthropic providers. To enable:
To disable: set mode: "off".

​
Pruning vs compaction

They complement each other — pruning keeps tool output lean between compaction cycles.

​
Further reading