let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: clarify cache-ttl pruning window

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-21 19:58:28 +00:00
parent c145a0d116
commit 6866cca6d7
2 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/concepts/session-pruning.md
View File

@@ -13,6 +13,7 @@ Session pruning trims **old tool results** from the in-memory context right befo
- Only affects the messages sent to the model for that request.
- Only active for Anthropic API calls (and OpenRouter Anthropic models).
- For best results, match `ttl` to your model `cacheControlTtl`.
- After a prune, the TTL window resets so subsequent requests keep cache until `ttl` expires again.
## What can be pruned
- Only `toolResult` messages.

1
docs/gateway/configuration.md
View File

@@ -1597,6 +1597,7 @@ Notes / current limitations:
- The estimated “context ratio” is based on **characters** (approximate), not exact tokens.
- If the session doesn’t contain at least `keepLastAssistants` assistant messages yet, pruning is skipped.
- `cache-ttl` only activates for Anthropic API calls (and OpenRouter Anthropic models).
- After a prune, the TTL window resets so subsequent requests keep cache until `ttl` expires again.
- For best results, match `contextPruning.ttl` to the model `cacheControlTtl` you set in `agents.defaults.models.*.params`.
Default (off):