From 73c5c06e31dd86a1f550becb39411b74ee36903a Mon Sep 17 00:00:00 2001
From: damocles <damocles@hyperhive.local>
Date: Mon, 7 Sep 2026 13:51:33 +0200
Subject: [PATCH] claude-settings: enable native auto-compact as a mid-turn
 safety net

---
 docs/turn-loop/claude-invocation.md     | 45 +++++++++++++++++++------
 hive-agent/prompts/claude-settings.json |  3 +-
 2 files changed, 36 insertions(+), 12 deletions(-)

diff --git a/docs/turn-loop/claude-invocation.md b/docs/turn-loop/claude-invocation.md
index 09b31224..34d2ddf5 100644
--- a/docs/turn-loop/claude-invocation.md
+++ b/docs/turn-loop/claude-invocation.md
@@ -86,12 +86,13 @@ context (it won't carry our title). claude stores sessions in
 `--name` writes the title into the file as a `custom-title` event, which
 is what `--resume <title>` resolves against. We never pass bare
 `--continue` (it resumes the _latest_ session in the cwd — the hijack
-vector). Auto-compact, auto-memory, and dynamic workflows (the `/workflows`
-feature) are disabled via the managed settings at
-`/etc/claude-code/managed-settings.json`: hyperhive owns compaction
-(see [Compaction](#compaction) below), and `disableWorkflows` keeps the
-`/workflows` machinery from spawning sub-runs that burn usage on the
-harness's autonomous turns.
+vector). Auto-memory and dynamic workflows (the `/workflows` feature) are
+disabled via the managed settings at `/etc/claude-code/managed-settings.json`:
+`disableWorkflows` keeps the `/workflows` machinery from spawning sub-runs
+that burn usage on the harness's autonomous turns. Claude's own native
+auto-compact is **on**, at the widest window claude-code allows — see
+[Compaction](#compaction) below for why (it's a safety net, not the
+primary mechanism; hyperhive still owns that).
 
 **Session reset** is available via `POST /api/new-session` (or
 `/new-session` slash command). It does _not_ touch the session inline —
@@ -105,10 +106,9 @@ turn's `--resume <title>` then misses and self-heals into a fresh session.
 
 ## Compaction
 
-claude's own in-session auto-compact is off (via the managed settings
-at `/etc/claude-code/managed-settings.json`); hyperhive owns it. The
-`hive_claude::InfiniteSession` keeps the session alive across the context
-window with two triggers baked into its `run`:
+hyperhive owns compaction as policy: the `hive_claude::InfiniteSession`
+keeps the session alive across the context window with two triggers baked
+into its `run`:
 
 - **Reactive** — claude-code prints `Prompt is too long`. The session is
   _already_ past the window, so no turn can run on it — the session
@@ -126,7 +126,30 @@ window with two triggers baked into its `run`:
   _then_ `/compact`s, so the agent can persist in-flight state before the
   detail collapses into a summary.
 
-The **when** is a `hive_claude::CompactionPolicy` injected by the harness:
+**Both triggers above are checked between hive-agent's own turns** — the
+percent watermark is read from the last completed turn's telemetry
+(`PercentPolicy::should_compact`, checked after `attempt()` returns), and
+the reactive path only fires once claude-code has already refused a whole
+turn as too long. Neither can see context growth happening _inside_ a
+single long turn's own tool-calling before it returns — a turn whose tool
+calls alone blow past the window hits the reactive path with no preceding
+checkpoint, losing whatever wasn't already persisted (#2707, root-caused in
+#3727).
+
+**Safety net for that gap: claude-code's own native auto-compact is on**,
+via the managed settings (`"autoCompactEnabled": true`,
+`"autoCompactWindow": 1000000` — the CLI's documented max, so it fires only
+right before the real hard limit, not as an earlier watermark). This is
+deliberately _not_ the primary mechanism — it runs with no checkpoint and
+none of the `CHECKPOINT_PROMPT` notes-flush machinery above, so a session
+saved by it still loses whatever wasn't already durable — but it can act
+_mid-turn_, underneath `InfiniteSession::run`, which the two triggers above
+structurally cannot. Do not confuse this with the `hyperhive.autoCompact`
+nix option below: that one is a per-agent on/off for hyperhive's _own_
+proactive watermark and has no effect on claude's native mechanism, which
+is fleet-wide and set once in `hive-agent/prompts/claude-settings.json`.
+
+The **when** for hyperhive's own policy is a `hive_claude::CompactionPolicy` injected by the harness:
 `turn::make_session` builds a `PercentPolicy` that compacts once the
 model-reported context fill reaches `HIVE_COMPACT_WATERMARK_PERCENT`
 (default **75%**), falling back to `harness_state::context_window_tokens(model)`
diff --git a/hive-agent/prompts/claude-settings.json b/hive-agent/prompts/claude-settings.json
index 06116fc0..8536c97d 100644
--- a/hive-agent/prompts/claude-settings.json
+++ b/hive-agent/prompts/claude-settings.json
@@ -1,5 +1,6 @@
 {
-  "autoCompactEnabled": false,
+  "autoCompactEnabled": true,
+  "autoCompactWindow": 1000000,
   "autoMemoryEnabled": false,
   "disableWorkflows": true,
   "permissions": {