From 12edd572c716ea9f481cd999a8a1586fbc8ce032 Mon Sep 17 00:00:00 2001
From: Lee Campbell <lee.ryan.campbell@gmail.com>
Date: Mon, 23 Mar 2026 07:57:21 +0800
Subject: [PATCH] fix: recover agent state on timeout instead of losing
 progress

When Claude timed out (exit 124), `set -euo pipefail` in agent-loop.sh
prevented sync_state from running, so all work from that iteration was
lost. Additionally, entrypoint.sh treated timeout as fatal and broke
the loop, preventing any retry.

Now run_claude captures the timeout exit code so sync_state always runs
to preserve progress, and entrypoint.sh continues the loop on timeout
so the next iteration can pick up where the previous one left off.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 autonomous/agent-loop.sh | 6 +++++-
 autonomous/entrypoint.sh | 6 ++++--
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/autonomous/agent-loop.sh b/autonomous/agent-loop.sh
index 88036dd..befc8dd 100644
--- a/autonomous/agent-loop.sh
+++ b/autonomous/agent-loop.sh
@@ -57,10 +57,12 @@ sync_state() {
     fi
 }
 
+CLAUDE_RC=0
+
 run_claude() {
     local prompt="$1"
     timeout "$CLAUDE_TIMEOUT" claude --dangerously-skip-permissions --print \
-        --output-format stream-json --verbose "$prompt"
+        --output-format stream-json --verbose "$prompt" || CLAUDE_RC=$?
 }
 
 load_prompt() {
@@ -288,3 +290,5 @@ EOF
         fi
         ;;
 esac
+
+exit $CLAUDE_RC
diff --git a/autonomous/entrypoint.sh b/autonomous/entrypoint.sh
index eb8d262..0c0be31 100644
--- a/autonomous/entrypoint.sh
+++ b/autonomous/entrypoint.sh
@@ -27,7 +27,7 @@ echo "Building..."
 dotnet build --no-restore
 
 # ── Run the agent ──
-MAX_ITERATIONS="${MAX_ITERATIONS:-10}"
+MAX_ITERATIONS="${MAX_ITERATIONS:-30}"
 COOLDOWN="${COOLDOWN_SECONDS:-30}"
 export CLAUDE_TIMEOUT="${TIMEOUT_SECONDS:-1800}"
 
@@ -39,9 +39,11 @@ for i in $(seq 1 "$MAX_ITERATIONS"); do
     EXIT_CODE=0
     bash /usr/local/bin/agent-loop.sh || EXIT_CODE=$?
 
-    if [ "$EXIT_CODE" -ne 0 ]; then
+    if [ "$EXIT_CODE" -ne 0 ] && [ "$EXIT_CODE" -ne 124 ]; then
         echo "Iteration $i failed with exit code $EXIT_CODE"
         break
+    elif [ "$EXIT_CODE" -eq 124 ]; then
+        echo "Iteration $i timed out (exit code 124), continuing..."
     fi
 
     # Done?