diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index 777e961fd..8b8229711 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -16,10 +16,12 @@
 - Changed `/btw`, `/tan`, `/omfg`, `/memory`, `/rename`, and `/move` to save the typed command text to TUI prompt history so they can be recalled with the up arrow.
 - Changed the temporary model picker to label Alt+P selections as session-only and point users to Alt+M or `/model` for role model assignment. ([#2952](https://github.com/can1357/oh-my-pi/issues/2952))
 - Replaced `new Promise((resolve, reject) => ...)` in `AsyncDrain` with `Promise.withResolvers()` per the repo's promise-construction convention
+- Changed the default advisor interrupt cooldown to 3 turns and the default auto-compaction strategy to snapcompact, with non-vision and over-budget snapcompact runs still falling back to context-full summaries.
 
 ### Fixed
 
 - Fixed a TypeError in `EventController` tests where a missing `settings` property in the `InteractiveModeContext` mock object led to calling `.get` on undefined when streaming tool-call args.
+- Fixed auto-compaction status text to label snapcompact runs instead of reporting them as context-full maintenance.
 - Fixed side-channel turns failing to correctly obfuscate secrets and tools when inheriting prompt cache layout
 - Fixed MCP startup status to live-update from "Connecting…" to connected, still-connecting, or failed server states so completed connections do not leave a stale banner. ([#3150](https://github.com/can1357/oh-my-pi/issues/3150))
 - Fixed session history becoming desynchronized when using the `rewind` tool
diff --git a/packages/coding-agent/src/prompts/advisor/system.md b/packages/coding-agent/src/prompts/advisor/system.md
index 652aa613a..a92c9e7cb 100644
--- a/packages/coding-agent/src/prompts/advisor/system.md
+++ b/packages/coding-agent/src/prompts/advisor/system.md
@@ -24,7 +24,7 @@ Keep exploration lean:
 - Offer alternatives, not lectures.
 - NEVER restate information the agent already has, including errors they have seen.
 - Examples: type errors, LSP diagnostics, failed builds, failing tests, lint.
-- NEVER repeat advice you already gave.
+- NEVER repeat advice you already gave, and NEVER send the same advice twice.
 - NEVER nitpick about things user stated they are okay with. You are the advocate for the user.
 </communication>