docs: nested goose hints (#8254)

Signed-off-by: Rizel Scarlett <rizel@entire.io>
This commit is contained in:
Rizel Scarlett
2026-04-02 09:27:15 -04:00
committed by GitHub
parent 710d9a3839
commit b92119c95a
2 changed files with 15 additions and 7 deletions
@@ -4,7 +4,7 @@ sidebar_position: 12
sidebar_label: Persistent Instructions
---
Persistent instructions let you inject text into goose's working memory every turn. Unlike [`.goosehints`](/docs/guides/context-engineering/using-goosehints) which are loaded once at session start, persistent instructions are re-read and injected fresh with every interaction. This makes them ideal for behavioral guardrails that must always be enforced, regardless of how the conversation evolves.
Persistent instructions let you inject text into goose's working memory every turn. Unlike [`.goosehints`](/docs/guides/context-engineering/using-goosehints), which are loaded at session start and can expand later when goose discovers nested hint files, persistent instructions are re-read and injected fresh with every interaction. This makes them ideal for behavioral guardrails that must always be enforced, regardless of how the conversation evolves.
## How It Works
@@ -116,7 +116,7 @@ unset GOOSE_MOIM_MESSAGE_TEXT
| Feature | Persistent Instructions | [goosehints](/docs/guides/context-engineering/using-goosehints) |
|---------|------------------------|-------------|
| When loaded | Every turn | Session start |
| When loaded | Every turn | Session start, plus nested context files discovered during the session |
| Can be forgotten | No | Yes, as context fills |
| Best for | Critical guardrails, security rules | Project context, coding standards |
| Token cost | Per turn | Once at start |