docs: refresh failover and compaction pattern refs

This commit is contained in:
Peter Steinberger
2026-04-04 20:43:58 +01:00
parent 97a587ddca
commit e336300e60
8 changed files with 39 additions and 19 deletions

View File

@@ -231,8 +231,9 @@ In the embedded Pi agent, auto-compaction triggers in two cases:
1. **Overflow recovery**: the model returns a context overflow error
(`request_too_large`, `context length exceeded`, `input exceeds the maximum
number of tokens`, `input is too long for the model`, and similar
provider-shaped variants) → compact → retry.
number of tokens`, `input token count exceeds the maximum number of input
tokens`, `input is too long for the model`, `ollama error: context length
exceeded`, and similar provider-shaped variants) → compact → retry.
2. **Threshold maintenance**: after a successful turn, when:
`contextTokens > contextWindow - reserveTokens`