From 400de54ff9afa0db5b0d93d4caa0d7c7eb37401c Mon Sep 17 00:00:00 2001
From: Mikei386 <44135113+Mikei386@users.noreply.github.com>
Date: Wed, 26 Aug 2026 06:54:57 +0200
Subject: [PATCH] Bound Hermes context compression latency

---
 platform/hermes/config.yaml         | 10 ++++++----
 platform/hermes/install-profiles.sh |  3 ++-
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/platform/hermes/config.yaml b/platform/hermes/config.yaml
index 77b51bd..0dd468c 100644
--- a/platform/hermes/config.yaml
+++ b/platform/hermes/config.yaml
@@ -78,8 +78,8 @@ agent:
       max_subagents: 8
 
 # Keep ample room for long agent work. Compression starts at 82% of whichever
-# router profile is selected and retains a useful 35% instead of collapsing a
-# large conversation to a tiny summary.
+# router profile is selected. Keep the result compact enough that a local
+# model does not spend many minutes generating the handoff.
 compression:
   enabled: true
   # Fold one older assistant/tool exchange into the rolling summary every five
@@ -90,14 +90,16 @@ compression:
   micro_compact_defrag_threshold_tokens: 2000
   progress_notices: true
   threshold: 0.82
-  target_ratio: 0.35
+  target_ratio: 0.15
   tail_mode: "lean"
   protect_last_n: 20
   protect_first_n: 0
   proactive_prune_tokens: 50000
   proactive_prune_min_result_chars: 4000
   proactive_prune_min_reclaim_tokens: 4096
-  context_total_ceiling_seconds: 600
+  # A failed local summarizer must not block an interactive client for ten
+  # minutes. Continue without dropping messages after two minutes.
+  context_total_ceiling_seconds: 120
 
 auxiliary:
   # Session names are cosmetic and used to create a second concurrent LLM
diff --git a/platform/hermes/install-profiles.sh b/platform/hermes/install-profiles.sh
index aadbc32..af883e3 100755
--- a/platform/hermes/install-profiles.sh
+++ b/platform/hermes/install-profiles.sh
@@ -33,7 +33,8 @@ create_profile() {
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.title_generation.enabled false
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config unset compression.threshold_tokens || true
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.threshold 0.82
-  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.target_ratio 0.35
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.target_ratio 0.15
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.context_total_ceiling_seconds 120
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.protect_last_n 20
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.protect_first_n 0
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.micro_compact true